Data-based identification of short term predictors for stock market trends using heterogeneous model ensembles

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

We here show the application of heterogeneous ensemble modeling for training short term predictors of trends in stock markets. A sliding window approach is used; model ensembles are iteratively learned and tested on subsequent data points. The goal is to predict trends (positive, neutral, or negative stock changes) for the next day, the next week, and the next month. Several machine learning approaches implemented in HeuristicLab and WEKA have been applied; the models produced using these methods have been combined to heterogeneous model ensembles. We calculate the final estimation for each sample via majority voting, and the relative ratio of a sample's majority vote is used for calculating the confidence in the final estimation; we use a confidence threshold that specifies the minimum confidence level that has to be reached. We show results of empirical tests performed using data of the Spanish stock market recorded from 2003 to 2013.

Original languageEnglish
Title of host publication26th European Modeling and Simulation Symposium, EMSS 2014
EditorsYuri Merkuryev, Lin Zhang, Emilio Jimenez, Francesco Longo, Michael Affenzeller, Agostino G. Bruzzone
PublisherDIME UNIVERSITY OF GENOA
Pages40-45
Number of pages6
ISBN (Electronic)9788897999324
Publication statusPublished - 2014
Event26th European Modeling and Simulation Symposium, EMSS 2014 - Bordeaux, France
Duration: 10 Sep 201412 Sep 2014

Publication series

Name26th European Modeling and Simulation Symposium, EMSS 2014

Conference

Conference26th European Modeling and Simulation Symposium, EMSS 2014
CountryFrance
CityBordeaux
Period10.09.201412.09.2014

Keywords

  • Ensemble modeling
  • Financial data analysis
  • Machine learning
  • Trend classification

Fingerprint Dive into the research topics of 'Data-based identification of short term predictors for stock market trends using heterogeneous model ensembles'. Together they form a unique fingerprint.

Cite this